def transform(self, data, options=None):
if self._validate(data) is None:
return None
arguments = { 'infile_data_suffix' : '.html' }
result = self.prepare_transform(data, arguments=arguments)
text = ''.join(result.data).decode('utf-8', 'ignore')
result.data = StringIter(html_bodyfinder(text))
return result
def transform(self, data, options=None):
if self._validate(data) is None:
return None
dev = self.dev
if options is not None:
dev = options.get("output_image_format", self.dev)
arguments = {"infile_data_suffix": ".html", "dev": "-dev %s" % dev}
result = self.prepare_transform(data, arguments=arguments)
if result.data is None:
return None
text = "".join(result.data).decode("utf-8", "ignore")
# workaround because of bug in pdftohtml
text = self.fixBrokenStyles(text)
result.data = StringIter(html_bodyfinder(text))
return result
def transform(self, data, options=None):
if self._validate(data) is None:
return None
data = u''.join(data)
return TransformResult(StringIter(html_bodyfinder(data)))
def extract_output(self, stdout):
return StringIter(html_bodyfinder(stdout.read()).decode("utf-8", "ignore"))
